Age Estimation and Face Verification Across Aging Using Landmarks

Age estimation and face verification across aging are important problems with a wide range of applications. It is well known that age and identity information are encoded in both texture and shape of the face. Building on recent advances in landmark extraction and statistical techniques for landmark...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on information forensics and security Vol. 7; no. 6; pp. 1780 - 1788
Main Authors Tao Wu, Turaga, P., Chellappa, R.
Format Journal Article
LanguageEnglish
Published IEEE 01.12.2012
Subjects
Online AccessGet full text
ISSN1556-6013
1556-6021
DOI10.1109/TIFS.2012.2213812

Cover

Abstract Age estimation and face verification across aging are important problems with a wide range of applications. It is well known that age and identity information are encoded in both texture and shape of the face. Building on recent advances in landmark extraction and statistical techniques for landmark-based shape analysis, we consider these problems using facial shapes. We show that by using well-defined shape spaces and their associated geometry, one can obtain significant performance improvements in both age estimation and face verification. Toward this end, we propose to model the facial shapes as points on a Grassmann manifold. Age estimation and face verification are then considered as regression and classification problems on this manifold. Algorithms for regression and classification are designed to take into account the geometry of the underlying space. The proposed method is flexible and can be used as a standalone age estimator or classifier, and we also present methods for fusion with texture-based algorithms.
AbstractList Age estimation and face verification across aging are important problems with a wide range of applications. It is well known that age and identity information are encoded in both texture and shape of the face. Building on recent advances in landmark extraction and statistical techniques for landmark-based shape analysis, we consider these problems using facial shapes. We show that by using well-defined shape spaces and their associated geometry, one can obtain significant performance improvements in both age estimation and face verification. Toward this end, we propose to model the facial shapes as points on a Grassmann manifold. Age estimation and face verification are then considered as regression and classification problems on this manifold. Algorithms for regression and classification are designed to take into account the geometry of the underlying space. The proposed method is flexible and can be used as a standalone age estimator or classifier, and we also present methods for fusion with texture-based algorithms.
Author Tao Wu
Turaga, P.
Chellappa, R.
Author_xml – sequence: 1
  surname: Tao Wu
  fullname: Tao Wu
  email: taowu@umiacs.umd.edu
  organization: Dept. of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA
– sequence: 2
  givenname: P.
  surname: Turaga
  fullname: Turaga, P.
  email: pturaga@asu.edu
  organization: Dept. of Arts Media & Eng., Arizona State Univ., Tempe, AZ, USA
– sequence: 3
  givenname: R.
  surname: Chellappa
  fullname: Chellappa, R.
  email: rama@umiacs.umd.edu
  organization: Dept. of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA
BookMark eNp9kM9OwzAMxiM0JLbBAyAufYGO2PnT9lhNG0yaxIGNa5Um7hTYOpT0wtuzrtMOHLjYluWf_fmbsFF7bImxR-AzAF48b1bL9xlywBkiiBzwho1BKZ1qjjC61iDu2CTGT86lBJ2PWVnuKFnEzh9M549tYlqXLI2l5IOCb7wduqUNxxiTcufbXbKNfVyfJg8mfMV7dtuYfaSHS56y7XKxmb-m67eX1bxcpxa16tJcgqmbDDk5yYVWAlRTK6odguIipyKXBeZSmAxV7QxJbrTT3DrrsLZZI6YMhr1nLYGa6jucVIefCnjVe1D1HlS9B9XFgxOT_WGs784vdcH4_b_k00B6Irpe0pihkJn4BayDauQ
CODEN ITIFA6
CitedBy_id crossref_primary_10_1007_s10462_019_09765_w
crossref_primary_10_1109_TPAMI_2017_2705122
crossref_primary_10_1049_iet_cvi_2018_5347
crossref_primary_10_1109_THMS_2014_2376874
crossref_primary_10_11834_jig_220842
crossref_primary_10_1111_exsy_12503
crossref_primary_10_1109_TIM_2015_2415012
crossref_primary_10_3390_sym10050148
crossref_primary_10_1016_j_patrec_2013_09_019
crossref_primary_10_1016_j_patcog_2022_109066
crossref_primary_10_1007_s41870_024_01872_4
crossref_primary_10_1049_iet_bmt_2016_0176
crossref_primary_10_1186_s13640_018_0324_4
crossref_primary_10_3390_s16070994
crossref_primary_10_1080_10798587_2016_1231471
crossref_primary_10_1109_TIFS_2020_3047753
crossref_primary_10_1088_1757_899X_928_3_032039
crossref_primary_10_1016_j_jvcir_2022_103452
crossref_primary_10_26634_jpr_1_2_2922
crossref_primary_10_1016_j_imavis_2018_05_003
crossref_primary_10_1007_s13369_018_3293_0
crossref_primary_10_1145_3090311
crossref_primary_10_1016_j_compeleceng_2016_01_001
crossref_primary_10_1007_s11042_019_7589_1
crossref_primary_10_1109_TPAMI_2014_2362759
crossref_primary_10_1049_iet_cvi_2017_0055
crossref_primary_10_1007_s00530_017_0555_8
crossref_primary_10_1109_TIFS_2017_2746062
crossref_primary_10_1155_2014_242846
crossref_primary_10_1007_s00414_014_1002_4
crossref_primary_10_1016_j_patcog_2015_12_015
crossref_primary_10_1049_iet_bmt_2016_0169
crossref_primary_10_1016_j_neucom_2016_01_101
crossref_primary_10_1186_s13640_018_0278_6
crossref_primary_10_1007_s11390_020_9665_4
crossref_primary_10_1016_j_patcog_2016_10_026
crossref_primary_10_1049_iet_bmt_2014_0053
crossref_primary_10_1186_1687_6180_2014_15
Cites_doi 10.1109/ICSMC.2009.5346730
10.1145/954339.954342
10.1109/34.993553
10.1109/FG.2011.5771410
10.1109/BTAS.2008.4699331
10.1137/S0895479895290954
10.1109/TPAMI.2007.70733
10.1109/TPAMI.2011.52
10.1007/978-3-540-77046-6_71
10.1109/FG.2011.5771424
10.1109/CVPR.2006.187
10.1109/BTAS.2009.5339037
10.1109/34.993558
10.1109/TIFS.2009.2038751
10.2307/1390631
10.1109/FG.2011.5771378
10.1016/j.cviu.2005.10.002
10.1109/AFGR.2008.4813365
10.1109/TIP.2006.884956
10.1145/1961189.1961199
10.1109/TSMCB.2003.817091
10.1109/FG.2011.5771329
10.1112/blms/16.2.81
10.1109/FG.2011.5771415
10.1016/S0262-8856(99)00012-8
10.1109/TPAMI.2010.36
10.1109/BTAS.2009.5339057
10.1002/cpa.3160300502
10.1109/TPAMI.2010.14
10.1109/BCC.2007.4430554
10.1109/CVPR.2005.153
10.1109/ICASSP.2010.5495292
10.1109/FG.2011.5771409
10.1109/TIP.2008.924280
10.1109/ICME.2007.4284917
10.1145/1390156.1390204
10.1109/CVPR.2011.5995564
10.1239/aap/1077134463
10.1109/SSP.2003.1289408
10.1109/ICCV.2007.4409050
10.1109/FG.2011.5771443
10.1109/FG.2011.5771411
10.1109/CVPR.2009.5206670
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TIFS.2012.2213812
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1556-6021
EndPage 1788
ExternalDocumentID 10_1109_TIFS_2012_2213812
6272347
Genre orig-research
GroupedDBID 0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFS
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
ID FETCH-LOGICAL-c265t-841abf720ed40365315fb5ebd215038e98492843a725bdae40a6d60cdcd2bc7f3
IEDL.DBID RIE
ISSN 1556-6013
IngestDate Wed Oct 01 03:15:36 EDT 2025
Thu Apr 24 23:00:06 EDT 2025
Tue Aug 26 17:18:10 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c265t-841abf720ed40365315fb5ebd215038e98492843a725bdae40a6d60cdcd2bc7f3
PageCount 9
ParticipantIDs crossref_primary_10_1109_TIFS_2012_2213812
ieee_primary_6272347
crossref_citationtrail_10_1109_TIFS_2012_2213812
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2012-12-01
PublicationDateYYYYMMDD 2012-12-01
PublicationDate_xml – month: 12
  year: 2012
  text: 2012-12-01
  day: 01
PublicationDecade 2010
PublicationTitle IEEE transactions on information forensics and security
PublicationTitleAbbrev TIFS
PublicationYear 2012
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref12
ref15
ref11
ref10
ref17
ref16
ref19
ref18
ref50
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref43
milborrow (ref25) 2010
ref49
segundo (ref36) 2010; 40
ref8
ref7
ref4
ramanathan (ref34) 2009; 15
ref3
ref6
ref5
ref40
ref35
ref37
ref31
ref30
ref33
ref32
ref2
ref39
ref38
milborrow (ref26) 2008
ref24
ref23
ref20
ref21
guo (ref14) 2008; 17
ref28
ref27
ref29
(ref1) 2000
fu (ref9) 2010; 32
liu (ref22) 2003; 1
References_xml – ident: ref27
  doi: 10.1109/ICSMC.2009.5346730
– ident: ref48
  doi: 10.1145/954339.954342
– ident: ref20
  doi: 10.1109/34.993553
– ident: ref46
  doi: 10.1109/FG.2011.5771410
– volume: 1
  start-page: 229i
  year: 2003
  ident: ref22
  article-title: Optimal linear representations of images for object recognition
  publication-title: Proc 2003 IEEE Computer Society Conf Computer Vision and Pattern Recognition 2003
– ident: ref3
  doi: 10.1109/BTAS.2008.4699331
– ident: ref7
  doi: 10.1137/S0895479895290954
– ident: ref12
  doi: 10.1109/TPAMI.2007.70733
– ident: ref44
  doi: 10.1109/TPAMI.2011.52
– ident: ref39
  doi: 10.1007/978-3-540-77046-6_71
– ident: ref31
  doi: 10.1109/FG.2011.5771424
– ident: ref33
  doi: 10.1109/CVPR.2006.187
– ident: ref50
  doi: 10.1109/BTAS.2009.5339037
– year: 2010
  ident: ref25
  publication-title: The MUCt Landmarked Face Database
– ident: ref2
  doi: 10.1109/34.993558
– start-page: 504
  year: 2008
  ident: ref26
  article-title: Locating facial features with an extended active shape model
  publication-title: Proc European Conf Computer Vision-Part I
– ident: ref21
  doi: 10.1109/TIFS.2009.2038751
– ident: ref13
  doi: 10.2307/1390631
– ident: ref23
  doi: 10.1109/FG.2011.5771378
– ident: ref38
  doi: 10.1016/j.cviu.2005.10.002
– ident: ref24
  doi: 10.1109/AFGR.2008.4813365
– ident: ref47
  doi: 10.1109/TIP.2006.884956
– ident: ref6
  doi: 10.1137/S0895479895290954
– volume: 40
  start-page: 1319
  year: 2010
  ident: ref36
  publication-title: Automatic Face Segmentation and Facial Landmark Detection in Range Images
– ident: ref4
  doi: 10.1145/1961189.1961199
– ident: ref19
  doi: 10.1109/TSMCB.2003.817091
– ident: ref49
  doi: 10.1109/FG.2011.5771329
– ident: ref18
  doi: 10.1112/blms/16.2.81
– volume: 15
  start-page: 3349
  year: 2009
  ident: ref34
  article-title: Age progression in human faces: A survey
  publication-title: J Vis Lang Comput
– ident: ref41
  doi: 10.1109/FG.2011.5771415
– ident: ref28
  doi: 10.1016/S0262-8856(99)00012-8
– volume: 32
  start-page: 1955
  year: 2010
  ident: ref9
  article-title: Age synthesis and estimation via faces: A survey
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2010.36
– ident: ref37
  doi: 10.1109/BTAS.2009.5339057
– ident: ref17
  doi: 10.1002/cpa.3160300502
– ident: ref30
  doi: 10.1109/TPAMI.2010.14
– ident: ref5
  doi: 10.1109/BCC.2007.4430554
– ident: ref32
  doi: 10.1109/CVPR.2005.153
– ident: ref43
  doi: 10.1109/ICASSP.2010.5495292
– year: 2000
  ident: ref1
  publication-title: Face and Gesture Recognition Working Group
– ident: ref35
  doi: 10.1109/FG.2011.5771409
– volume: 17
  start-page: 1178
  year: 2008
  ident: ref14
  article-title: Image-based human age estimation by manifold learning and locally adjusted robust regression
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2008.924280
– ident: ref10
  doi: 10.1109/ICME.2007.4284917
– ident: ref15
  doi: 10.1145/1390156.1390204
– ident: ref16
  doi: 10.1109/CVPR.2011.5995564
– ident: ref40
  doi: 10.1239/aap/1077134463
– ident: ref11
  doi: 10.1109/SSP.2003.1289408
– ident: ref45
  doi: 10.1109/ICCV.2007.4409050
– ident: ref29
  doi: 10.1109/FG.2011.5771443
– ident: ref8
  doi: 10.1109/FG.2011.5771411
– ident: ref42
  doi: 10.1109/CVPR.2009.5206670
SSID ssj0044168
Score 2.3302271
Snippet Age estimation and face verification across aging are important problems with a wide range of applications. It is well known that age and identity information...
SourceID crossref
ieee
SourceType Enrichment Source
Index Database
Publisher
StartPage 1780
SubjectTerms Age estimation
biometrics
Estimation
Face recognition
face verification
facial shapes
Feature extraction
Grassmann manifold
Manifolds
Shape analysis
Title Age Estimation and Face Verification Across Aging Using Landmarks
URI https://ieeexplore.ieee.org/document/6272347
Volume 7
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1556-6021
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0044168
  issn: 1556-6013
  databaseCode: RIE
  dateStart: 20060101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLbGTnBgsIEYL-XACdGRpnl0xwptAsS48BC3Kg-XA7ChsV349SRtNw2EELeqsqXUjms7sT8DnPgQNJZpgREtfLrKU5tE2jAdMYyRJp6LlXBNo1t5-cCvn8RTA86WvTCIWBafYS88lnf5bmLn4ajsXDLFEq7WYE2lsurVWvx1vVev2t6EkJFPMpL6BjOm_fP7q-FdKOJiPcZi76HYNx-0MlSl9CnDFowWq6lKSV5685np2c8fQI3_Xe4WbNbBJcmq3bANDRy3obUY3EBqO27DxgoKYQey7BnJwJt61cVI9NiRobZIHj1BUZ_pkaz8FpKFoUakLDQgN57yTU9fPnbgYTi4v7iM6skKkWVSzKKUx9oUilF03Lswb4eiMAKN8wEATVLsp7zv_VaiFRPGaeRUSyepddYxY1WR7EJzPBnjHhCthGBGswCMxp00IWJDjUo4o-Ii5V2gC1nntoYdD9MvXvMy_aD9PKgnD-rJa_V04XTJ8l5hbvxF3AmSXxLWQt___fUBrAfmqh7lEJqz6RyPfFQxM8fldvoCToLG6g
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLZgHIADjwFiPHPghOiWpkkfxwoxDdi4sKHdqjxcDoOBYLvw60n6mAAhxK2qnCi149pO7M8AZ9YF9cM4R4_mNlzlsQ48qZj0GPpIAzuKFXBNg7uwN-I3YzFegotFLQwiFsln2HaPxV2-edFzd1TWCVnEAh4tw4rgnIuyWqv-71q7Xha-CRF6NswIqjtMnyad4XX33qVxsTZjvrVR7JsV-tJWpbAq3U0Y1Ospk0km7flMtfXHD6jG_y54CzYq95Kk5X7YhiWcNmGzbt1AKk1uwvoXHMIdSNNHJFdW2cs6RiKnhnSlRvJgCfLqVI-kxbeQ1LU1IkWqAelbymf5NnnfhVH3anjZ86reCp5moZh5MfelyiNG0XBrxKwmilwJVMa6ADSIMYl5Yi1XICMmlJHIqQxNSLXRhikd5cEeNKYvU9wHIiMhmJLMQaNxEyrns6HESBgV-XnMW0BrXme6Ah53_S-esiIAoUnmxJM58WSVeFpwvhjyWqJu_EW84zi_IKyYfvD761NY7Q0H_ax_fXd7CGtuojI75Qgas7c5HlsfY6ZOiq31Ceheyjc
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Age+Estimation+and+Face+Verification+Across+Aging+Using+Landmarks&rft.jtitle=IEEE+transactions+on+information+forensics+and+security&rft.au=Wu%2C+Tao&rft.au=Turaga%2C+Pavan&rft.au=Chellappa%2C+Rama&rft.date=2012-12-01&rft.issn=1556-6013&rft.eissn=1556-6021&rft.volume=7&rft.issue=6&rft.spage=1780&rft.epage=1788&rft_id=info:doi/10.1109%2FTIFS.2012.2213812&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIFS_2012_2213812
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1556-6013&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1556-6013&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1556-6013&client=summon